DF-TransFusion: Multimodal Deepfake Detection via Lip-Audio Cross-Attention and Facial Self-Attention.

Aaditya Kharel Manas Paranjape Aniket Bera

Published in: CoRR (2023)

Keyphrases

multi modal
object detection
detection algorithm
automatic detection
detection accuracy
landmark detection
audio visual speech recognition
multimedia
selective attention
focus of attention
audio visual
information gain
facial images
detection method
signal processing
low level
feature vectors